_edited_edited.png)
Living in this pandemic has made almost all of us very frequent online shoppers on platforms like Amazon, some of us more frequent Netflix viewers, and some of us spending more time watching Youtube videos if we weren’t doing all of that already(as in my case ;-) and we can’t help but notice the recommendation systems that these e-commerce websites/apps use. Besides increasing sales for these companies, it has actually helped us(the customers) a lot especially now, when we have to manage everything from home, alongside working all day from home.
That means there is no need for making grocery lists anymore or wasting a great deal of time searching for the right kind of clothes for your babies. You make a click at one item, other items pop up recommending us to buy which other customers like us have bought.
These recommendations typically speed up searches and make it easier for users to access the content they’re interested in and surprise them with offers they would have never searched for. We began to feel known and understood and in most cases buy the things that we desire to own one day eventually even if not needed, or making more time to watch a movie or a video that is recommended to us that we would not have even searched ever, thereby increasing the revenue for these top giants like Amazon, NetFlix, YouTube, etc.
Seeing its powerfulness, no doubt it has been in use for more than a decade now.
So what are recommendation systems?
A recommendation system is an information filtering system that seeks to predict the "rating" or "preference" a user would give to an item.
It is broadly classified into two types based on the data being used to make inferences:
Content-based filtering, which uses item(catalog) attributes.
Collaborative filtering, which uses user behavior or interactions in addition to items attributes.
In this article, I am going to explore more about collaborative filtering.
So, what is Collaborative filtering?
Collaborative filtering is the most common way to do product recommendations online. It’s “collaborative” because it predicts a given customer’s preferences on the basis of other customers’.
These kinds of systems utilize user interactions to filter for items of interest. We can visualize the set of interactions with a matrix, where each entry (m, n) where (m,n) represents the interaction between user m and item n. An interesting way of looking at collaborative filtering is to think of it as a generalization of classification and regression. While in these cases we aim to predict a variable that directly depends on other variables (features), in collaborative filtering, there is no such distinction between feature variables and class variables.
Collaborative filtering is based on the assumption that people who agreed in the past will agree in the future, and that they will like similar kinds of items as they liked in the past. The system generates recommendations using only information about rating profiles for different users or items.
We cannot really generalize the use of Collaborative Filtering as every company in the market is using its own model. Amazon uses Item-to-Item Collaborative Filtering.
What is Item-to-Item Collaborative Filtering?
While the world has been focusing on user-based Collaborative Filtering, Amazon came up with the algorithm where product recommendations are not just on similarities between customers but on correlations between products in 2003. With item-to-item collaborative filtering, the recommendation algorithm would review the visitor’s recent purchase history and, for each purchase, pull up a list of related items. Items that showed up repeatedly across all the lists were candidates for recommendation to the visitor. But those candidates were given greater or lesser weight depending on how related they were to the visitor's prior purchases.
That notion of relatedness is still derived from customers’ purchase histories: item B is related to item A if customers who buy A are unusually likely to buy B as well. But Amazon’s Personalization team found, empirically, that analyzing purchase histories at the item level yielded better recommendations than analyzing them at the customer level.
So, the recommendation algorithms provide an effective way of targeted marketing by creating a personalized shopping experience for every customer. In the future, we would not be surprised to see the retail industry to more broadly apply recommendation algorithms for targeted marketing, both online and offline. While e-commerce businesses have the easiest vehicles for personalization, the technology’s increased conversion rates as compared with traditional broad-scale approaches will also make it compelling to offline retailers for use in postal mailings, coupons, and other forms of customer communication.